© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39785
    Prev
    Next
    INDEX
    Explanations

    number one or rank

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of “1” marking a top rank or first pick (e.g. “No. 1”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    這些
    -2.16
     japonaise
    -1.91
    尛
    -1.81
    <bos>
    -1.76
     econó
    -1.75
     '
    -1.73
    这些
    -1.72
    źdz
    -1.70
     bemerkt
    -1.70
     vuestro
    -1.70
    POSITIVE LOGITS
     и
    1.95
     also
    1.94
    ↵
    1.90
     và
    1.88
    ø
    1.81
    a
    1.80
    sto
    1.77
    na
    1.76
    s
    1.75
    now
    1.73
    Activations Density 0.030%

    No Known Activations